[NET-652] [Alert EdvwWb] ink-sepolia_No_Dumper_Data

[elina-chertova]

Automated fix proposal for alert EdvwWb.

• Alert: ink-sepolia_No_Dumper_Data
• Base branch: open-beta
• Investigation: /root/alert/incident-agent/agent-system/data/investigations/EdvwWb
• Report: /root/alert/incident-agent/agent-system/data/investigations/EdvwWb/report.html

Reviewer quick view

• Scope: 1 file(s) in evm
• Root cause (agent): not explicitly captured
• Summary: response now.

● Write FINAL_RESPONSE.md (shell)
│ cat > /root/alert/incident-agent/agent-system/data/investigations/EdvwWb/t
│ erminal_debate/EdvwWb__terminal_debate__20260521_105615/FINAL_RESPONSE.md
│ << 'ENDOFFILE'
│ # FINAL RESPONSE — EdvwWb: ink-sepolia_No_Dumper_Data…
└ 205 lines...

● FINAL RESPONSE written. Here's the summary:

Verdict: accept_with_changes (implementer patch is correct; one PR-note addition)

Root cause confirmed [evidence]: dump-ink-sepolia-0 is in CrashLoopBackOff (5 restarts) because
every Ink Sepolia block contains an OP-Stack type-0x7e deposit transaction with no nonce field,
but rpc-data.ts:221 declares nonce: SMALL_QTY (required). This causes DataValidationError at
rpc.js:997 on every eth_getBlockByNumber call → crash → loop.

Fix (one line, open-beta):

evm/evm-rpc/src/rpc-data.ts:221

• nonce: SMALL_QTY,

• nonce: option(SMALL_QTY),

Staged at fixes/proposed/evm/evm-rpc/src/rpc-data.ts — diff verified (1 line only).

Operator actions required:

1. Merge PR → build new evm-dump image
2. Update image tag in infra chart
3. ArgoCD sync → verify pod Running without new restarts

PR note: add tx.nonce != null guard in the Cronos phantom-tx loop at rpc.ts:471/483 as defensive
hygiene (not a blocker for this incident).

Temporary mitigation (if build cycle > few hours): comment out ink-sepolia.yaml in infra to stop
the crash loop — explicitly NOT the fix.

Fix metadata

• Fix class: rca_fix
• Confidence: high
• Evidence basis: logs, code
• Falsification: if QuikNode ink-sepolia RPC returns "nonce":"0x0" on deposit txs —
• Follow-up: verify dump-ink-sepolia-0 runs >5 min without restart and blocks
  (Generated by the terminal-debate agent — values reflect the agent's self-assessment, not a verified verdict. Use them as a starting point for review.)

Summary

response now.

● Write FINAL_RESPONSE.md (shell)
│ cat > /root/alert/incident-agent/agent-system/data/investigations/EdvwWb/t
│ erminal_debate/EdvwWb__terminal_debate__20260521_105615/FINAL_RESPONSE.md
│ << 'ENDOFFILE'
│ # FINAL RESPONSE — EdvwWb: ink-sepolia_No_Dumper_Data…
└ 205 lines...

● FINAL RESPONSE written. Here's the summary:

Verdict: accept_with_changes (implementer patch is correct; one PR-note addition)

Root cause confirmed [evidence]: dump-ink-sepolia-0 is in CrashLoopBackOff (5 restarts) because
every Ink Sepolia block contains an OP-Stack type-0x7e deposit transaction with no nonce field,
but rpc-data.ts:221 declares nonce: SMALL_QTY (required). This causes DataValidationError at
rpc.js:997 on every eth_getBlockByNumber call → crash → loop.

Fix (one line, open-beta):

evm/evm-rpc/src/rpc-data.ts:221

• nonce: SMALL_QTY,

• nonce: option(SMALL_QTY),

Staged at fixes/proposed/evm/evm-rpc/src/rpc-data.ts — diff verified (1 line only).

Operator actions required:

1. Merge PR → build new evm-dump image
2. Update image tag in infra chart
3. ArgoCD sync → verify pod Running without new restarts

PR note: add tx.nonce != null guard in the Cronos phantom-tx loop at rpc.ts:471/483 as defensive
hygiene (not a blocker for this incident).

Temporary mitigation (if build cycle > few hours): comment out ink-sepolia.yaml in infra to stop
the crash loop — explicitly NOT the fix.

Risk & rollout

• Suggested rollout: canary / one-network-first, then broader rollout after signal is stable.
• Rollback: revert this PR (or restore previous config values/files) if the incident signal worsens.

Reproduction status

Incident behavior was reproduced or corroborated strongly enough for a non-hypothesis fix proposal.

Validation checklist

• Verify the original incident signal improves (logs/metrics/alerts) after deploy.
• Verify no regression on sibling networks/providers/services touched by this change.
• Confirm queue / delivery pipeline status returns to expected steady state.

Changed files

• evm/evm-rpc/src/rpc-data.ts

Notify

cc @tmcgroul (automation opened this PR.)